ResearchTasksOut-of-scope refusalFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedScienceQA out-of-scope (test)Prompt-based0Refusal Rate40Feb 26, 2026MMMU out-of-scope (test)Prompt-based0.18Refusal Rate9Feb 26, 2026